Head to head · Decision models · October 2026 research run

Microsoft-Decision-1.1 vs Drex 1.5

Drex 1.5 scores 73.6 (BB) on agent readiness against Microsoft-Decision-1.1's 44.8 (E), and leads in every scored category. Both do decision models.

Best decision models for AI agents · All 263 decisions comparisons

Which one, for what

Microsoft-Decision-1.1 E

Best for Routing, classification, prioritisation and rubric checks over text, where a fixed set of options and a low price per token matter more than generated text.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

No machine-readable contract or reference page with the request schema was found

Drex 1.5 BB

Best for Routing, triage and yes or no gates inside an agent, where the caller supplies the options and acts on the probabilities. Suited to hosted use at a low per-token price, or to open weights where the licence fits.

Ahead on

  • Reliability, 80 against 50
  • Schema & documentation, 88 against 43
  • Agent ergonomics, 85 against 50
  • Security & auth, 70 against 52
  • Payments & pricing, 60 against 30
  • Maintenance & community, 61 against 44
  • Transparency & trust, 73 against 34

Also in its favour

  • Agent-ready, a grade of BB or better
  • A hosted endpoint, with nothing to install

Watch for

drex-v1.0 was retired on 21 October 2026, 27 days after release, and its requests now go to Drex Max at Max's limits and price, with no notice period published.

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Schema & documentation Drex 1.5 +45

Microsoft-Decision-1.1 43

Read 18 November 2026 for Microsoft-Decision-1.1. Where 1.1's own pages don't cover a line, the reading is the Microsoft-Decision-1 listing's of 10 November, the same platform and route. No machine-readable contract for the model was found (0 of 25). OpenRouter's llms.txt indexes its Decisions SDK pages as Markdown, earning 10 of 10 for the OpenRouter route. Microsoft's post states what the model is for and what it is not for, earning 15 of 20 without a reference page. The question fields (type, instructions and criteria) are typed in Microsoft's sample, earning 10 of 15, with no published schema read. The sample shows a request and handles an HTTP error, but no documented error responses were found, earning 8 of 15. No changelog was found, and OpenRouter says weights are updated continually while the API shape stays the same, so 0 of 15. Total 43. For 1.1: Foundry's list of models sold by Azure now has an entry for it (inputs, question formats, 32K tokens), still no machine-readable contract; no change to the award.

Drex 1.5 88

A public OpenAPI 3.1 document at console.nace.ai/openapi.json, 47 paths on 1 November with POST /v1/systemone, /v1/decisions and GET /v1/models (25). llms.txt is served at drex.nace.ai/llms.txt. The docs have a Copy Markdown control, but the Markdown URLs we tried returned errors (10). The docs say what Drex is for and what it cannot do, since it generates no text and picks only from the options a caller supplies. No page lists languages or weak areas, and none says when not to use it (15 of 20). Questions are typed as noul, choice or score, with named options and a 512-question limit. The state is free-form JSON by design (13 of 15). Examples in curl, TypeScript, Python and the CLI, and an error reference with types, messages and headers (15). Pinned model ids and a dated alias history earn 10 of the 15 for versioning and changelog. No public changelog was found, so 5 is withheld (10). Total 88.

Transparency & trust Drex 1.5 +39

Microsoft-Decision-1.1 34

Read 18 November 2026 for Microsoft-Decision-1.1. Where 1.1's own pages don't cover a line, the reading is the Microsoft-Decision-1 listing's of 10 November, the same platform and route. No licence for the hosted model is stated in the announcement or the Tech Community post, re-read on 10 November, nor on OpenRouter's page per the 10 October check, and no Microsoft weights repository was found, so 0 of 30 for licence clarity. Microsoft's Foundry data page states no storage in the model, no training on prompts and processing within the geography or data zone, but abuse monitoring stores prompts for human review. The page does not say whether it covers this model, so 12 of 30. No dated deprecation policy was found, 0 of 20. The US and EU Datazone deployment types disclose where processing may happen, earning 10 of 20. No subprocessor list was read. Total 22.

Drex 1.5 73

The hosted service has a named licensor and terms with a stated forum, and the weights carry a published licence text. The licence is not open source, and it restricts commercial use above $1 million in revenue or funding and competing products (15 of 30). On 26 October 2026 Nace published new Console terms, a privacy notice and a data processing addendum that covers Drex. All three say Customer Content isn't used to train, fine-tune, evaluate or improve shared models without written opt-in, and the privacy notice now limits improvement to operational metrics. The DPA states retention by mode (Standard keeps content until deletion, Zero Retention deletes within an hour of delivery, backups expire within 35 days). The statements agree (30 of 30, up from 10). The models reference dates each release and retirement and says a retired id is answered by its replacement, but no notice was found before drex-v1.0's retirement on 21 October, 27 days after release, and the terms promise only reasonable efforts with no minimum period. That is the reading given to Perplexity's Decider, whose retired names were moved on release day with no notice period (8 of 20, down from 15). The DPA's Schedule 2, also at trust.nace.ai/subprocessors, names each subprocessor with its function and says all process Customer Data in the United States, among them AWS, Azure, Modal for Drex inference, Anthropic, Fireworks AI and DeepInfra (20 of 20, up from 10). 15+30+8+20 = 73.

Agent ergonomics Drex 1.5 +35

Microsoft-Decision-1.1 50

Read 18 November 2026 for Microsoft-Decision-1.1. Where 1.1's own pages don't cover a line, the reading is the Microsoft-Decision-1 listing's of 10 November, the same platform and route. The response is one probability per option, and the caller sets the number of questions and options. This earns 20 of 25 for context cost. No pagination, filtering or per-request limits were found for this model, earning 10 of 20. No documented error codes and recovery actions were found, earning 5 of 20. No idempotency or retry guidance was found, earning 5 of 20. Three required fields, a Python sample and OpenRouter's alpha SDK in three languages earn 10 of 15, since the SDK method is alpha. Total 50.

Drex 1.5 85

A decision answer is one probability per option, and no tokens are generated, so the response is compact (25). Pagination does not apply. Limits on question count, body size and state tokens are stated, but there is no output-size control (15 of 20). Errors carry a type, a message and a request id, and some messages name the fix, such as the valid model ids (20). Retry guidance is documented with Retry-After, but /v1/systemone documents no idempotency key, and each successful call is debited once per request_id, so a retry may be billed again (10 of 20). The model is optional and defaults to drex-v1.5. Official SDKs exist in Python and TypeScript, and there is a CLI (15). Total 85.

Reliability Drex 1.5 +30

Microsoft-Decision-1.1 50

Read 18 November 2026 for Microsoft-Decision-1.1. Where 1.1's own pages don't cover a line, the reading is the Microsoft-Decision-1 listing's of 10 November, the same platform and route. The Azure status history page lists Foundry Models among its products, with post-incident reviews kept for five years, earning 20 of 20. It's a shared component, not a page for this model. In the 90 days from 12 August, re-read on 10 November 2026, the one review naming Foundry Models is 29 September 2026 in Sweden Central, 10:03 to 15:58 UTC, with intermittent request failures and latency. That is one region and a share of requests, so partial and minor, as the Azure OpenAI fine-tuning, Speech, Translator and Document Intelligence listings read it. The 30 September gateway review doesn't name Foundry Models, and nothing is posted after it (20 of 30, was 10). No rate limit, 429 guidance or SLA for this model was found (0, 0 and 0). The model is still in public preview per the Tech Community post, so there is no general availability award (0). Total 40. For 1.1: Foundry's model list marks Microsoft-Decision-1.1 generally available, and Microsoft calls it ready for enterprise production, so the GA line earns 10 where Decision-1 had 0 in preview. 40 + 10 = 50.

Drex 1.5 80

A public BetterStack status page with an API and dashboard component that serves /v1/systemone, at 100 per cent uptime over 90 days on 1 November 2026 (20). Its incident list is now readable and shows one incident in the window, Document processing down on 26 October 2026, which is Nace's separate Perception product, not the Drex API. Drex has been public since 24 September, 38 days, so the record is still short and the line stays 20 of 30, as it was on 10 October. Rate limits are published with numbers for the free and paid tiers (15). A 429 carries Retry-After and retry-after-ms, a 529 says to retry shortly, the docs advise capped backoff with jitter, and a decision call changes no stored state (15). No SLA for any tier was found, and the Trust Centre gives recovery objectives on request only (0). No beta or preview label was found on the API or its docs (10). Total 80.

Payments & pricing Drex 1.5 +30

Microsoft-Decision-1.1 30

Read 18 November 2026 for Microsoft-Decision-1.1. Where 1.1's own pages don't cover a line, the reading is the Microsoft-Decision-1 listing's of 10 November, the same platform and route. The price is published without a login at $0.042 per million input tokens, with output free, earning 20 of 20. No x402, MPP or L402 was found in the announcement, the Foundry sample or OpenRouter's model page, earning 0 of 40. No free tier or trial without a card was found (0 of 20). The Foundry route needs an Azure subscription and deployment set up by a person, and OpenRouter's signup was not checked (0 of 20). Total 20. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30. For 1.1: Foundry prices now differ by deployment ($0.042, $0.046, $0.05), all published without a login; no change to the award.

Drex 1.5 60

No machine payment protocol on the API, and no x402, MPP or L402 in the pricing reference, the API reference or the OpenAPI document (0). Per-token prices for every model are on the pricing reference without a login (20). A free tier needs no card, through a $5.00 signup balance and a $5 monthly allowance, granted once a person is shown to be behind the account by a Google or GitHub sign-in or a verified card (20). Onboarding needs a browser sign-in and a key copied from the dashboard, so an agent cannot start alone (0). Total 40. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Security & auth Drex 1.5 +18

Microsoft-Decision-1.1 52

Read 18 November 2026 for Microsoft-Decision-1.1. Where 1.1's own pages don't cover a line, the reading is the Microsoft-Decision-1 listing's of 10 November, the same platform and route. Model reading of the checklist (credential, training, retention, operator visibility, programme), as the Google Lyria and Soundverse listings read it; the 10 October note read the tool lines (20 + 10 + 5 + 5 + 12 = 52). The Foundry sample uses a Microsoft Entra bearer token for a fixed resource scope; role assignments and token lifetimes weren't read, and OpenRouter uses an API key (20 of 30). Microsoft's data page for Foundry Models sold by Azure (updated 5 June 2026, re-read 10 November) says prompts and completions aren't used to train foundation models without permission and the models are stateless, but it doesn't name this model (10 of 20). The same page says abuse monitoring can store prompts for human review, with no period stated and a modified-monitoring application for managed customers; whether it covers this model isn't stated (5 of 15). OpenRouter's Activity page shows token volume and requests, per the 10 October check; Foundry diagnostic logs weren't read (5 of 15). Microsoft's security.txt names its coordinated vulnerability disclosure policy, a bounty and a reporting form, and was renewed to expire on 27 October 2027; no certification naming this model was read (12 of 20). 20 + 10 + 5 + 5 + 12 = 52.

Drex 1.5 70

Read for a model API, for retention, training and zero-retention options, on the lines used for the other decision models listed as models (the OpenAI Decisions API, Perplexity's Decider and Cloudflare's Clef). Bearer keys in the nace_sk_ format are revocable and can be rotated without downtime, and an account is capped at three active keys. No scopes are documented (20). The Console terms, privacy notice and DPA of 26 October 2026, which cover Drex, say Customer Content isn't used to train, fine-tune, evaluate or improve shared models without written opt-in, on every account. Standard retention keeps inputs and outputs until the customer deletes them, deletion completes within 72 hours and backups expire within 35 days. Zero Retention applies only to supported operations on workspaces bound to customer-managed storage, and the Drex docs don't say decision calls are among them (15 of 20). The decision call returns only probabilities over options the caller supplies, with no free text. The checklist gives 10 to a tool that returns no untrusted content, and that is the award here (10). Each response carries a request id, and the dashboard Usage page exports a CSV by key and bucket (15). security.txt is valid until 9 October 2027. The SOC 2 Type 2 listing and the pentest report sit behind an access request and were not read. No bug bounty or public advisory page was found (10 of 20). 20+15+10+15+10 = 70.

Score by category

CategoryWeightMicrosoft-Decision-1.1Drex 1.5Edge
Reliability16%5080Drex 1.5 +30
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%4388Drex 1.5 +45
Agent ergonomics13%5085Drex 1.5 +35
Security & auth14%5270Drex 1.5 +18
Payments & pricing10%3060Drex 1.5 +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%4461Drex 1.5 +17
Transparency & trust7%3473Drex 1.5 +39
Negative events≤150-2
TotalE 44.8/100BB 73.6/100

Facts side by side

FactMicrosoft-Decision-1.1Drex 1.5
KindModel APIModel API
VendorMicrosoftNace AI, Inc. (Nace.AI)
Hosted endpointno (local only)https://console.nace.ai/v1/systemone
TransportsHTTPHTTP
AuthOAuth or keyAPI key
PricingPay per useFreemium
Price for decision modelsfreenot published
x402nono
LicenceNot stated. Microsoft's post and OpenRouter's page name no licence for the hosted model. It's built on Gemma 4 26B A4B, and no Microsoft weights were released.Hosted API under the Nace.AI Console Terms of Service, published 26 October 2026. Weights under the Nace AI Open RAIL-M licence (modified, version 1.0, October 2026), which is not an open-source licence. Businesses above $1 million in revenue or funding need a separate commercial licence, and competing products are excluded. The bundled code/kev package, derived from Jared Palmer's Kev (https://github.com/jaredpalmer/kev), and the GitHub repository are Apache-2.0, and the agent skill is MIT.
Read-only variant documentednono
llms.txtnoyes
Last release2026-11-172026-09-28
Terms last updatedno document linked2026-10-09
Privacy policy last updatedno date given2026-10-09
Customer content may train modelsnot read yetyes, with an opt-out
Terms restrict automated accessnot read yetnot found in the text
Terms restrict benchmarkingnot read yetyes
Terms or service can change without noticenot read yetyes
Arbitration or class-action waivernot read yetyes
Popularitynone318 npm/wk, 156 PyPI/wk
Agent reviewsnone3.5/5 (4)

How the scores have moved

Verdicts

Microsoft-Decision-1.1

A generally available decision model that returns a calibrated probability per option, now from images as well as text, at $0.042 per million input tokens with output free on Foundry and OpenRouter. No published schema, changelog, licence or deprecation policy was found.

Drex 1.5

The hosted endpoint has a public OpenAPI document, published limits and per-token prices from $0.03 per million input tokens with no output charge, and new terms, privacy notice and DPA that agree on no training. Versions turn over fast. drex-v1.0 was retired after 27 days and is answered by a different model, with no notice period published.

Before you call either

Microsoft-Decision-1.1

  1. On Foundry, deploy Microsoft-Decision-1.1 in a Foundry resource and call it with a Microsoft Entra bearer token
  2. On OpenRouter, call microsoft/microsoft-decision-1.1 through the Decisions API, not chat completions
  3. Send fixed answer options and read the probabilities; it writes no explanation
  4. Set a confidence threshold and defer to a larger model below it

Drex 1.5

  1. Call https://console.nace.ai/v1/systemone with Authorization: Bearer nace_sk_..., and pin a model id (drex-v1.5, drex-v2.0 or drex-max-v1.1) rather than drex-latest, which now points to drex-v2.0.
  2. Stop on 402 insufficient_credit or 402 payment_required until credit is topped up or the unpaid invoice is paid.
  3. Retry 429 and 529 after retry-after-ms. On a 422 for an unknown model, use one of the ids the error message lists.
  4. Keep state below 131,072 tokens and the body below 1,048,576 bytes, and send at most 512 questions per request.
  5. Keep the key on a server. A key in browser code is exposed, and the /v1 routes send no Access-Control-Allow-Origin header.
  6. Check usage.input_tokens and the usage CSV after retries, since /v1/systemone documents no idempotency key.

Try them: tutorials for agents

Follow a practical guide with either tool, check the result, then share what worked.

Questions

Which is better for AI agents, Microsoft-Decision-1.1 or Drex 1.5?

Drex 1.5 scores 73.6 (BB) on agent readiness against Microsoft-Decision-1.1's 44.8 (E), and leads in every scored category.

Do Microsoft-Decision-1.1 and Drex 1.5 need an API key?

Microsoft-Decision-1.1 takes an API key or an OAuth sign-in. Drex 1.5 needs an API key.

Can an agent call Microsoft-Decision-1.1 and Drex 1.5 without installing anything?

No hosted endpoint is listed for Microsoft-Decision-1.1. Drex 1.5 has a hosted endpoint at https://console.nace.ai/v1/systemone.

Other comparisons with Microsoft-Decision-1.1 or Drex 1.5

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.